© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35407
    Prev
    Next
    INDEX
    Explanations

    words starting with W

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åºľ
    -0.09
    岸
    -0.09
    LETE
    -0.09
    atement
    -0.09
    lement
    -0.09
    ghi
    -0.08
    ä¸įèī¯ä¿¡æģ¯
    -0.08
    é¹ij
    -0.08
    ÑģÑĮ
    -0.08
    å¦Ī
    -0.08
    POSITIVE LOGITS
    ings
    0.11
    ylie
    0.10
    iggins
    0.10
    nings
    0.09
    åĮ»æĬ¤
    0.09
    tower
    0.09
    ritable
    0.09
    -Fi
    0.09
    inston
    0.08
    çĤ¸
    0.08
    Activations Density 0.071%

    No Known Activations